Model evaluation for pr

• Climate variables used as response: - sfcWind, tas, pr: original scale daily, reduced scale: hourly - clt, rsds: original scale monthly, reduced scale: daily

• Training: All models are trained using ERA5 in reduced scale as observations. Training data perdiod: 1980 - 2015.

• Validation Period: 2015-01-02 00:00:00 to 2023-12-30 23:00:00

• Response variable to predict: upscaled ERA5 (daily or monthly)

• Predictors variables: daily scale the variables sfcWind, tas, pr, tasmax, tasmin and psl and in a monthly scale clt, rsdt,rsds , the month , hour, sun’s elevation & azimuth and the daily daylight amount in seconds.

Numerical evaluation metrics

• Each row correspond an evaluation metric
• Dark blue cell indicates the best model in the row.
• Light blue cell indicates the second best model in the row.

Metric	xgboost	cnn	naive	lstm	xgboost_custom
mae	0.07	0.07	0.09	0.07	0.09
cor	0.88	0.87	0.83	0.86	0.86
ratio_of_sd	0.86	0.93	0.81	0.87	1.01
KGE	0.81	0.78	0.69	0.80	0.56
amplitude_mae	0.16	0.13	0.22	0.14	0.13
maximum_difference	6.20	6.31	6.29	6.30	6.00
sign_correlation	0.60	0.55	0.60	0.60	0.58
extreme_correlation	0.58	0.69	0.52	0.64	0.65
amount_rainy_hours_mae	1.55	1.55	2.23	1.69	2.62
qqplot_mae	0.02	0.02	0.04	0.02	0.05
acf_mae	0.10	0.06	0.14	0.07	0.10
extremogram_mae	0.06	0.03	0.07	0.03	0.05

Graphical evaluation metrics

• Observations: cumulative distribution (Detrended QQ), dependency structure (ACF), and extremes (Extremogram, using 0.97 cut off).

• Daily/Monthly gruped: Maximum hour histogram (only in daily variables), Amplitude distribution.

• Hourly/Daily grouped: Mean profile per hour within days (or weeks witihin season)

• In all plots, grey color represent the true ERA5 signal.